Alternatives and similar repositories for Math-PUMA

Users that are interested in Math-PUMA are comparing it to the libraries listed below

• njucckevin / MM-Self-Improve
  A Self-Training Framework for Vision-Language Reasoning
  ☆86Updated 8 months ago
• yuezih / less-is-more
  Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)
  ☆55Updated 11 months ago
• LightChen233 / M3CoT
  ☆82Updated last year
• RifleZhang / LLaVA-Reasoner-DPO
  ☆92Updated 9 months ago
• luka-group / mDPO
  [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.
  ☆81Updated 11 months ago
• opendatalab / HA-DPO
  Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
  ☆94Updated last year
• NUS-TRAIL / NoisyRollout
  [NeurIPS 2025] NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
  ☆92Updated 3 weeks ago
• njucckevin / CapArena
  An Arena-style Automated Evaluation Benchmark for Detailed Captioning
  ☆55Updated 4 months ago
• RupertLuo / VoCoT
  VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models
  ☆74Updated last year
• MikeWangWZHL / PAPO
  Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"
  ☆86Updated last month
• TideDra / VL-RLHF
  A RLHF Infrastructure for Vision-Language Models
  ☆184Updated 10 months ago
• vlf-silkie / VLFeedback
  ☆100Updated last year
• OpenGVLab / V2PE
  [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding
  ☆57Updated 10 months ago
• ShadeCloak / ADORA
  ☆46Updated 6 months ago
• 1zhou-Wang / MemVR
  [ICML 2025] Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in…
  ☆157Updated 2 weeks ago
• zwq2018 / Multi-modal-Self-instruct
  The codebase for our EMNLP24 paper: Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Mo…
  ☆83Updated 8 months ago
• X-PLUG / mPLUG-HalOwl
  mPLUG-HalOwl: Multimodal Hallucination Evaluation and Mitigating
  ☆98Updated last year
• yaolinli / DeCo
  Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models
  ☆71Updated 2 months ago
• RUCAIBox / Virgo
  Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*
  ☆109Updated 4 months ago
• Liuziyu77 / MMDU
  Official repository of MMDU dataset
  ☆95Updated last year
• findalexli / mllm-dpo
  [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model
  ☆47Updated 11 months ago
• LALBJ / PAI
  [ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs
  ☆145Updated 11 months ago
• AoiDragon / POPE
  [EMNLP'23] The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''
  ☆93Updated last month
• NiuTrans / Vision-LLM-Alignment
  This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vi…
  ☆115Updated 3 months ago
• MME-Benchmarks / MME-CoT
  MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiency
  ☆130Updated 2 months ago
• pengshuai-rin / MultiMath
  MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models
  ☆31Updated 8 months ago
• YiyangZhou / LURE
  [ICLR 2024] Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
  ☆149Updated last year
• Yuqifan1117 / HalluciDoctor
  HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data (Accepted by CVPR 2024)
  ☆48Updated last year
• TIGER-AI-Lab / VL-Rethinker
  The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]
  ☆155Updated 4 months ago
• yihedeng9 / STIC
  Enhancing Large Vision Language Models with Self-Training on Image Comprehension.
  ☆70Updated last year